Imported code from GitHub repo

README.md

@@ -1,12 +1,76 @@
----
-title: Text Sentiment Api
-emoji: 📈
-colorFrom: blue
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.31.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Text-Sentiment-Classifier-API
+This project is a simple REST API for sentiment analysis built with FastAPI and HuggingFace Transformers. It uses the distilbert-base-uncased-finetuned-sst-2-english model to classify English text as positive,  negative or (rarely) neutral, and it returns a confidence score.
+
+# 🚀 Features
+
+- RESTful API with FastAPI
+
+- Pre-trained BERT-based sentiment model
+
+- JSON input and output
+
+- Interactive Swagger UI at /docs
+
+# 📦 Model
+
+The API uses:
+
+`` distilbert-base-uncased-finetuned-sst-2-english ``
+
+A lightweight version of BERT fine-tuned on the SST-2 dataset for sentiment classification.
+
+# Example
+
+Request:
+``
+POST /predict
+{ 
+  "text": "I absolutely love this product!" 
+}
+``
+
+Response:
+``
+{ 
+  "sentiment": "positive", 
+  "confidence": 0.9981 
+}
+``
+
+# 📁 File Structure
+
+. </br>
+├── main.py               # API implementation </br>
+├── requirements.txt      # Python dependencies </br>
+└── README.md             # Project documentation </br>
+
+
+## 🚀 How to Use
+
+1. Enter any English sentence in the input box
+2. Click **Submit**
+3. View the sentiment label and confidence
+
+
+## 🚀 How to Deploy on Hugging Face Spaces
+
+1. Create a Hugging Face account <br>
+   Sign up at https://huggingface.co/join
+
+2. Create a new Space
+   Go to https://huggingface.co/spaces and click Create new Space
+
+3. Fill out the form
+   - Space name: text-sentiment-api (or your choice)
+   - SDK: Gradio
+   - Visibility: Public or Private
+
+4. Upload the files
+   - app.py
+   - requirements.txt
+   - README.md (this file)
+
+5. Wait for the build 
+   Hugging Face will automatically install dependencies and launch the app
+
+6. Access your app

app.py

@@ -0,0 +1,32 @@
+#!/usr/bin/python3
+
+"""  
+    This file launches a simple web interface using Gradio to classify text sentiment 
+    (positive/negative) using a pre-trained DistilBERT model. It is designed to run 
+    locally or directly on Hugging Face Spaces.
+    
+    @author mtzortzi
+"""
+
+import gradio as gr
+from transformers import pipeline
+
+# Load sentiment analysis model
+sentiment_analyzer = pipeline("sentiment-analysis", model = "distilbert-base-uncased-finetuned-sst-2-english")
+
+def analyze_sentiment(text):
+    result = sentiment_analyzer(text)[0]
+    label = result['label'].capitalize()
+    score = round(result['score'], 4)
+    return f"Sentiment: {label} (Confidence: {score})"
+
+# Gradio interface
+iface = gr.Interface(
+    fn=analyze_sentiment,
+    inputs=gr.Textbox(lines=3, placeholder="Enter a sentence for sentiment analysis..."),
+    outputs="text",
+    title="Text Sentiment Classifier",
+    description="Classifies text as Positive or Negative using a DistilBERT model trained on SST-2."
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.110.0
+uvicorn==0.29.0
+transformers==4.40.1
+torch>=1.13
+pydantic==1.10.13
+gradio==4.25.0
+